Akshay Sharma comments

Results 15 comments of


                                            Akshay Sharma

module 'tensorflow' has no attribute 'gfile'

@nobillygreen Thank you man for this hack

preporcessing issue

Hi @zsLin177 I have not solved this.

Issue with multiple input quantization(tf savedmodel)

Hi @chensuyue sorry I can't share the model

Issue with multiple input quantization(tf savedmodel)

Hi @chensuyue is there any update? One piece of information which I can share is that it has a transformer layer in it.

Issue with multiple input quantization(tf savedmodel)

Hi @lvliang-intel actually I am trying using `dataset = quantizer.dataset('dummy', shape=[(1,256),(1,256)])` dummy data without using yaml file. Have you tried that or YAML file is compulsory for bert type of...

TypeError: forward() missing 1 required positional argument: 'img_meta

Hi @chaobeiying, this is might happen because your model required 1 more input. I hope this will helps.

Testing on custom questions/queries

Hi, @Param-Raval have you solved this issue as I am facing the same issue(on Sparc dataset).

Testing on custom questions/queries

Hi @Param-Raval thanks for the response but the issue is due to OOV as described in the below issue https://github.com/ryanzhumich/editsql/issues/21 Hence Solving OOV issue has solved this issue.

how to pre-process custom data to be the format of being ready to be trained?

Have anyone figure out this?

Loss could not converge when training from scratch

Hi @anti-machinee. my dataset is different but I am facing a similar issue my loss is also around 16. Have you solved this issue?